learning_rate: 0.0001
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 22
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	2.2759	34	0.6978	0.4167	0.2451	0.1736	0.4167
No log	4.5517	68	0.6822	0.5833	0.4298	0.3403	0.5833
No log	6.8276	102	0.6700	0.5833	0.4298	0.3403	0.5833
0.6972	9.0690	136	0.6680	0.6042	0.4752	0.7642	0.6042
0.6972	11.3448	170	0.6412	0.6458	0.5562	0.7796	0.6458
0.6972	13.6207	204	0.6277	0.625	0.5172	0.7717	0.625
0.6502	15.8966	238	0.5148	0.7708	0.7674	0.7702	0.7708
0.6502	18.1379	272	0.5042	0.7917	0.7898	0.7907	0.7917
0.6502	20.4138	306	0.6177	0.7708	0.7715	0.7729	0.7708

davidqm/wav2vec2-large-xls-r-300m-dm32

wav2vec2-large-xls-r-300m-dm32